[index-tts]windows，用文档里的方法安装依赖后运行报错，_kaldifst动态链接库(DLL)初始化示例程序失败。

from _kaldifst import (

ImportError: DLL load failed while importing _kaldifst: 动态链接库(DLL)初始化例程失败。

使用uv安装了依赖库 uv sync --default-index "https://mirrors.aliyun.com/pypi/simple" .venv里查看没有问题

运行的cuda toolkit也安装了驱动支持的最高版本

出错的脚本是这个 from indextts.infer_v2 import IndexTTS2

tts = IndexTTS2(cfg_path="checkpoints/config.yaml", model_dir="checkpoints", use_fp16=False, use_cuda_kernel=False, use_deepspeed=False) text = "酒楼丧尽天良，开始借机竞拍房间，哎，一群蠢货。" tts.infer(spk_audio_prompt='examples/voice_07.wav', text=text, output_path="gen.wav", emo_audio_prompt="examples/emo_sad.wav", verbose=True)

需要下载的其他内容也全下完了，以下是全部输出

GPT weights restored from: checkpoints\gpt.pth GPT2InferenceModel has generative capabilities, as prepare_inputs_for_generation is explicitly overwritten. However, it doesn't directly inherit from GenerationMixin. From 👉v4.50👈 onwards, PreTrainedModel will NOT inherit from GenerationMixin, and this model will lose the ability to call generate and other related functions.

• If you're using trust_remote_code=True, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
• If you are the owner of the model architecture code, please modify your model class such that it inherits from GenerationMixin (after PreTrainedModel, otherwise you'll get an exception).
• If you are not the owner of the model architecture class, please contact the model code owner to update it. Failed to load custom CUDA kernel for BigVGAN. Falling back to torch. semantic_codec weights restored from: ./checkpoints/hf_cache\models--amphion--MaskGCT\snapshots\265c6cef07625665d0c28d2faafb1415562379dc\semantic_codec\model.safetensors cfm loaded length_regulator loaded gpt_layer loaded s2mel weights restored from: checkpoints\s2mel.pth campplus_model weights restored from: ./checkpoints/hf_cache\models--funasr--campplus\snapshots\fb71fe990cbf6031ae6987a2d76fe64f94377b7e\campplus_cn_common.bin Loading weights from nvidia/bigvgan_v2_22khz_80band_256x Removing weight norm... bigvgan weights restored from: nvidia/bigvgan_v2_22khz_80band_256x

Traceback (most recent call last): File "E:\code\index-tts-main\script.py", line 3, in tts = IndexTTS2(cfg_path="checkpoints/config.yaml", model_dir="checkpoints", use_fp16=False, use_cuda_kernel=False, use_deepspeed=False) File "E:\code\index-tts-main\indextts\infer_v2.py", line 160, in init self.normalizer.load() File "E:\code\index-tts-main\indextts\utils\front.py", line 95, in load from wetext import Normalizer File "E:\code\index-tts-main.venv\lib\site-packages\wetext__init.py", line 15, in from wetext.utils import ( File "E:\code\index-tts-main.venv\lib\site-packages\wetext\utils.py", line 18, in from wetext.constants import FSTS File "E:\code\index-tts-main.venv\lib\site-packages\wetext\constants.py", line 14, in from kaldifst import TextNormalizer as normalizer File "E:\code\index-tts-main.venv\lib\site-packages\kaldifst\init__.py", line 1, in from _kaldifst import ( ImportError: DLL load failed while importing _kaldifst: 动态链接库(DLL)初始化例程失败。